Page tools: Print Page Print All | ||
|
INTRODUCTION
9 Trend estimates help the user to identify the underlying magnitude and direction of a time series. Seasonal adjustment removes the effect of the last three listed influences from the data, leaving only trend and short-term irregular movements. Trend estimates are then obtained by removing the effects of the short-term irregularities, which in some series can be a major contributor to movements in the original data. 10 Trend estimates are produced by smoothing the seasonally adjusted series using a statistical procedure based on Henderson moving averages. At each time point in a series, a trend estimate is calculated using a centred x-term Henderson moving average of the seasonally adjusted series. The moving averages are centred on the point in time at which the trend is being estimated. The number of terms used to calculate the trend varies across surveys. Generally, ABS monthly surveys use a 13-term moving average and quarterly surveys use a 7-term moving average. 11 Estimates for the most recent time points cannot be calculated using the centred average method as there are insufficient data to do so. Instead, alternative approaches that approximate the smoothing properties of the Henderson moving average are used. This can lead to revision in the trend estimates for the most recent time periods until sufficient data are available to calculate the trend using the centred Henderson moving average. Revisions of trend estimates will also occur with revisions to the original data and re-estimation of seasonal adjustment factors. 12 Seasonal factors are reviewed annually for most ABS labour series, to take account of each additional year's original data. The results of the latest reviews were used to compile the trend estimates given in this publication. Information about the most recent annual review of seasonal factors for the LFS was published in a feature article in the February 2003 issue of Labour Force, Australia (cat. no. 6203.0). For further information about the most recent reviews of seasonal factors for the labour employer surveys, see the following publications:
13 The general methods used in the ABS for estimating trends are described in Information Paper: A Guide to Smoothing Time Series - Estimates of Trend (cat. no. 1316.0). RELIABILITY OF ESTIMATES 14 Estimates in this publication are subject to two types of error:
15 For more information on these sources of error, and on measures of these types of errors, including standard errors, refer to the main publications associated with each of the data series presented in this publication (see the relevant sections later in these Explanatory Notes). More information on standard errors applying to LFS estimates is contained in Information Paper: Labour Force Survey Standard Errors (cat. no. 6298.0), due to be released in mid-2003. ROUNDING 16 Estimates have been rounded and discrepancies may occur between sums of the component items and totals. LABOUR FORCE SURVEY DATA Description of the survey 17 Data in tables 1.1-1.7, 2.1-2.10, 3.1-3.3, 4.3 and 4.4 are obtained from the Labour Force Survey (LFS), which provides extensive information about the labour market on a monthly basis. The LFS is a component of the Monthly Population Survey (MPS), which includes the LFS and supplementary surveys. Monthly Population Survey 18 The MPS is a population survey based on a multi-stage area sample of private dwellings (currently about 30,000 houses, flats, etc.), and list samples of discrete Indigenous communities and non-private dwellings (hospitals, hotels, motels, etc.), and covers about 0.5% of the population of Australia. The information is obtained from occupants of selected dwellings by interviewers, with the first interview conducted face-to-face and subsequent interviews over the telephone. Once selected, households are included for eight consecutive months before being replaced. Labour Force Survey 19 The LFS has been conducted on a monthly basis since February 1978. Prior to that, from 1964 to 1978, a national survey was conducted quarterly. Telephone interviewing was introduced between August 1996 and February 1997. New questionnaires have been introduced periodically, most recently in April 2001. 20 The LFS includes all usual residents of Australia aged 15 and over except:
21 From July 1993, Jervis Bay Territory has been excluded from the scope of the LFS. Supplementary surveys 22 The supplementary surveys collect additional data on a different topic each month. Many topics covered are rotated on an annual or less frequent basis, while others are included once only. Results from each supplementary survey topic are released separately. A list of topics covered in recent years is in Appendix 3. 23 Tables 4.1 and 4.2 contain data from the annual supplementary surveys Underemployed Workers and Persons Not in the Labour Force. These tables are updated annually. 24 The supplementary surveys include a subset of the persons included in the LFS (see paragraph 20). The additional exclusions for most supplementary surveys are:
Reference period 25 Interviews are generally conducted during the two weeks beginning on the Monday between the 6th and 12th of each month, with questions relating to the week prior to the interview (the reference week). 26 From time to time, changes to survey methodology affect the time series produced. Some examples of changes to this survey are: new questions added to the LFS questionnaire in April 2001; and the introduction of telephone interviewing in 1996-97. Population benchmarks 27 LFS estimates of persons employed, unemployed and not in the labour force are calculated in such a way as to add up to independently estimated counts (benchmarks) of the civilian population aged 15 years and over. These benchmarks are based on Census data adjusted for under-enumeration and updated for births, deaths, interstate migration, and net permanent and long-term migration. This procedure compensates for under-enumeration in the survey, and leads to more reliable estimates. 28 Population benchmarks used in the estimation of LFS data are revised after each Census, when population estimation bases are reviewed. These revisions affect original, seasonally adjusted and trend estimates. The last such revision was made in February 1999 to take account of the results of the 1996 Census. This revision affected all monthly estimates from January 1995 to January 1999. The next revision is scheduled for February 2004 to take account of the results from the 2001 Census. Families series 29 Family relationship is not determined for all households and persons in scope of the LFS. This is due to a number of factors related to the scope and coverage of the LFS, as well as difficulties in determining family structure and characteristics. The survey questions used to determine family relationships are restricted to persons enumerated as usual residents of private dwellings. That is, the following persons are excluded:
30 In addition, in those households where it is not possible to obtain information relating to all the usual residents, no family information is recorded. Thus, persons living in households which include a member of the permanent defence forces, who is outside the scope of the LFS, are excluded from survey questions used to determine family relationships. This also applies to households that, at the time of the survey, had one or more of their usual residents away for more than six weeks, and households from which an incomplete or inadequate questionnaire was obtained for any usual resident in scope of the survey. Further information and data on the LFS 31 LFS estimates are published monthly in Labour Force, Australia (cat. no. 6202.0). A series of time-series spreadsheets are released at the same time as this publication. More detailed estimates are released, in electronic format, later each month. All electronic data can be accessed via the ABS web site. Additional data are available on request. 32 For further information about the range of LFS products and services, and the concepts and methodology used in the LFS, refer to Information Paper: Changes to Labour Force Survey Products (cat. no. 6297.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), or contact the Assistant Director, Labour Force Survey on Canberra 02 6252 6565. EMPLOYER SURVEY DATA 33 Tables 2.11, 5.1-5.3, 6.1-6.2 and 7.1 of this publication contain data from ABS employer surveys. Scope of employer surveys 34 Except where otherwise noted, the ABS labour employer surveys are selected from the ABS Business Register, which is primarily based on registrations to the Australian Taxation Office's (ATO) Pay As You Go Withholding scheme and (prior to 1 June 2000) the Group Employer scheme. The population is updated quarterly to take account of new businesses, business that have ceased employing, changes in employment levels, changes in industry, and other general business changes. Businesses excluded from the scope of the employer surveys are:
JOB VACANCIES DATA 35 Table 7.1 contains data from the Job Vacancies Survey (JVS). Description of the survey 36 The current Job Vacancies Survey has been conducted since November 1983 and is a quarterly sample survey of approximately 4,600 employers. The survey produces estimates of the number of job vacancies in Australia. Reference date 37 The reference date for the survey is the third Friday of the middle month of the quarter. Notes on data 38 Prior to the August quarter 1999, job vacancies statistics were collected as part of the Job Vacancies and Overtime Survey. The overtime component of the survey ceased following the May quarter 1999. Further information 39 For further information about the range of products and services relating to ABS job vacancies statistics, and the concepts and methodology used, refer to Job Vacancies, Australia (cat. no. 6354.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), the associated time series spreadsheets available from the ABS web site, or contact the Manager, Job Vacancies Survey on Perth 08 9360 5304. PUBLIC SECTOR EMPLOYEES DATA Description of the survey 40 Data in table 2.11 are obtained from a quarterly survey of public sector businesses: the Survey of Employment and Earnings (SEE). This survey has been conducted on a quarterly basis since the September quarter 1983. The survey measures both the number of public sector wage and salary earners employed in the middle month of each quarter and their total quarterly earnings. Reference period 41 The reference period for employees is the last pay period ending on or before the third Friday of the middle month of the quarter. The reference period for gross earnings is all pay periods which end within the quarter. Notes on data 42 The private sector component of the Survey of Employment and Earnings was discontinued after the December quarter 2001. Further information 43 For further information about the range of products and services relating to public service employees, and the concepts and methodology used, refer to Wage and Salary Earners, Public Sector, Australia (cat. no. 6248.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), or contact the Manager, Survey of Employment and Earnings, Public Sector on Perth 08 9360 3141. AVERAGE WEEKLY EARNINGS DATA 44 Table 5.2 contains data from the Survey of Average Weekly Earnings (AWE). Description of the survey 45 The Survey of Average Weekly Earnings has been conducted quarterly since August 1981. Approximately 4,700 businesses contribute to the survey each quarter. The purpose of the survey is to measure average gross weekly earnings per employee job in Australia. 46 Average weekly earnings statistics represent average gross (before tax) earnings of employees and do not relate to average award rates nor to the earnings of the 'average person'. Estimates of average weekly earnings are derived by dividing estimates of weekly total earnings by estimates of number of employees. Changes in the averages may be affected not only by changes in the level of earnings of employees but also by changes in the overall composition of the wage and salary earner segment of the labour force. Reference period 47 The reference period for the survey is the last pay period ending on or before the third Friday of the middle month of the quarter. For non-weekly payrolls, businesses are asked to provide one week's portion. Further information 48 For further information about the range of products and services relating to average weekly earnings refer to Average Weekly Earnings, Australia (cat. no. 6302.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), the associated time series spreadsheets available from the ABS web site, or contact the Manager, Survey of Average Weekly Earnings on Perth 08 9360 5304. WAGE COST INDEX DATA 49 Table 5.1 contains data from the Wage Cost Index, Australia (cat. no. 6345.0) publication. Description of the survey 50 The Wage Cost Index (WCI) is a price index which measures changes over time in wage and salary costs for employee jobs, unaffected by changes in the quality or quantity of work performed. Changes in wages and salaries resulting from changes in the composition of the labour market are excluded from the WCI movements. Index numbers have been compiled and published since December quarter 1997 (with a reference base of September quarter 1997 = 100.0). Approximately 19,000 matched jobs from 4,100 qualifying businesses are priced each quarter. Reference period 51 The reference period for the survey is the last pay period ending on or before the third Friday of the mid-month of the quarter. Notes on data 52 The Wage Cost Index collection methodology has not changed since its inception in September quarter 1997. Seasonally adjusted data 53 Experimental seasonally adjusted data have been released in Wage Cost Index, Australia (cat. no. 6345.0), commencing with the June quarter 2002 edition. The data is likely to continue to be noted as 'experimental' for at least the first two years the series are published. 54 The WCI uses a concurrent seasonal adjustment methodology to derive adjustment factors for its experimental seasonally adjusted series. This method uses the whole series available at each reference quarter to estimate seasonal factors. Concurrent adjustment can result in revisions each quarter to seasonally adjusted estimates for earlier periods, although the most significant change is likely to occur in the last quarter of the series previously published. 55 For more information about seasonally adjusted estimates from the WCI, see Wage Cost Index, Australia (cat. no. 6345.0) and the article titled Seasonally Adjusting the Wage Cost Index: Experimental Estimates, published in the April 2002 edition of Australian Economic Indicators (cat. no. 1350.0). Further information 56 For further information about the range of products and services relating to the Wage Cost Index, and the concepts and methodology used, refer to Wage Cost Index, Australia (cat. no. 6345.0), Information Paper: Wage Cost Index, Australia (cat. no. 6346.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), the associated time series spreadsheets available from the ABS web site, or contact the Labour Price Index Output Group on Perth 08 9360 5151. INDUSTRIAL DISPUTES DATA 57 Tables 6.1 and 6.2 contain data from the Industrial Disputes collection. Description of the survey 58 The ABS has been collecting information about industrial disputes since 1913. The Industrial Disputes collection produces estimates of the number of industrial disputes (where ten or more working days are lost), employees involved, and working days lost. 59 The scope of the Industrial Disputes collection is restricted to employing businesses at which an industrial dispute has occurred. For this collection, industrial disputes are defined as work stoppages of ten working days or more. Ten working days are equivalent to the amount of ordinary time worked by ten people in one day, regardless of the length of the stoppage, e.g. 3,000 workers on strike for two hours would be counted as 750 working days lost (assuming they work an eight-hour day). 60 Effects on other establishments not directly involved in the dispute, such as stand-downs because of lack of materials, disruption of transport services, power cuts, etc. are not included in the scope of this collection. Reference period 61 The collection reference period is the calendar month. Data on working days lost are collated and published on a quarterly basis in this publication. Further information 62 For further information about the range of products and services relating to ABS industrial disputes statistics, and the concepts and methodology used, refer to Industrial Disputes, Australia (cat. no. 6321.0), Labour Statistics: Concepts, Sources and Methods (cat. no. 6102.0), the associated time series spreadsheets available from the ABS web site, or contact the Manager, Industrial Disputes on Perth 08 9360 5159. NATIONAL ACCOUNTS DATA 63 Table 5.3 contains data from the Australian National Accounts. 64 Estimates of compensation of employees are contained within the Income Accounts of the Australian National Accounts, which are published in Australian System of National Accounts (cat. no. 5204.0) and Australian Economic Indicators (cat. no. 1350.0). For further information on how estimates are obtained, see Australian System of National Accounts: Concepts, Sources and Methods (cat. no. 5216.0). INTERNATIONAL DATA 65 Table 1.8 contains data from the International Labour Organisation. 66 Estimates of key indicators of the labour markets from various countries have been included for comparison with Australian estimates of labour force participation, employment, unemployment and unemployment rates. Document Selection These documents will be presented in a new window.
|